Acupuncture has reportedly improved memory and cognitive impairment in both animal and clinical studies. It may be an effective treatment for Alzheimer's disease (AD). The purpose of this meta-analysis was to review the effectiveness of acupuncture for the treatment of AD. Eight databases were searched for articles published up to and including July 2017, and 13 studies fulfilling the inclusion criteria were identified. The main outcomes assessed were clinical efficacy rate, Mini-Mental State Examination score, Ability of Daily Living Scale score, Alzheimer's Disease Assessment Scale-Cognition score, Hasegawa's Dementia Scale (HDS) score, and adverse events. The methodological quality of the articles was assessed using Cochrane's risk of bias. All the studies compared the efficacy of acupuncture with that of medication, and were published in Chinese journals. Meta-analysis revealed that acupuncture yielded positive results as determined via all the indexes scored except the HDS (95% CI -0.26 to 0.90, Z=0.35, P=0.73). Only one of the studies reported adverse events associated with acupuncture and medication. The rate of adverse events in the medication group was 13%. In most of the studies assessed in the current meta-analysis, acupuncture alone was better than conventional western medicines for the treatment of AD.